How does COVID and loneliness affect mental health?
2025-05-06
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.1
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
## Loading required package: Matrix
##
##
## Attaching package: 'Matrix'
##
##
## The following objects are masked from 'package:tidyr':
##
## expand, pack, unpack
##
##
##
## Attaching package: 'lmerTest'
##
##
## The following object is masked from 'package:lme4':
##
## lmer
##
##
## The following object is masked from 'package:stats':
##
## step
##
##
## Loading required package: MASS
##
##
## Attaching package: 'MASS'
##
##
## The following object is masked from 'package:dplyr':
##
## select
##
##
## Loading required package: mvtnorm
##
## Loading required package: sandwich
##
## mediation: Causal Mediation Analysis
## Version: 4.5.1
##
##
## This is lavaan 0.6-19
## lavaan is FREE software! Please report any bugs.Descriptive Stats
1. OVERALL SAMPLE CHARACTERISTICS
## === OVERALL SAMPLE CHARACTERISTICS ===## Total observations: 12909## Unique participants: 4303## Observations per wave:##
## 1 2 3
## 4303 4303 43032. DESCRIPTIVE STATISTICS BY WAVE
##
## === DESCRIPTIVE STATISTICS BY WAVE ===## # A tibble: 27 × 5
## wave `General Health Questionnaire_1` Malaise_1 Generalised Anxiety Disord…¹
## <dbl> <dbl> <dbl> <dbl>
## 1 1 4303 4069 4086
## 2 1 2.44 1.21 5.32
## 3 1 0.92 1.68 2.21
## 4 1 1 0 4
## 5 1 2 0 4
## 6 1 2 1 4
## 7 1 3 2 6
## 8 1 5 9 16
## 9 1 0 234 217
## 10 2 4302 4279 4273
## # ℹ 17 more rows
## # ℹ abbreviated name: ¹​`Generalised Anxiety Disorder_1`
## # ℹ 1 more variable: `Loneliness Scale_1` <dbl>3. CATEGORICAL VARIABLES BY WAVE
##
## === CATEGORICAL VARIABLES BY WAVE ===## Covid Positive Cases by Wave:## # A tibble: 3 × 6
## wave `0` `1` `NA` Total Percent_Positive
## <dbl> <int> <int> <int> <int> <dbl>
## 1 1 4065 237 1 4302 5.5
## 2 2 3977 292 34 4269 6.8
## 3 3 3864 418 21 4282 9.8##
## Hospitalised by Wave:## # A tibble: 3 × 5
## wave `0` `1` Total Percent_Hospitalised
## <dbl> <int> <int> <int> <dbl>
## 1 1 4294 9 4303 0.2
## 2 2 4292 11 4303 0.3
## 3 3 4283 20 4303 0.5##
## Household Number Distribution by Wave:## # A tibble: 3 × 6
## wave N Mean_HHNUM SD_HHNUM Min_HHNUM Max_HHNUM
## <dbl> <int> <dbl> <dbl> <dbl+lbl> <dbl+lbl>
## 1 1 4303 2.14 1.08 0 20
## 2 2 4303 2.08 0.92 1 10
## 3 3 4303 2.07 0.92 1 104. DETAILED FREQUENCY TABLES
##
## === DETAILED FREQUENCY TABLES ===## GHQ Score Distribution by Wave:## # A tibble: 17 × 5
## # Groups: wave [3]
## wave GHQ n percent cum_percent
## <dbl> <dbl+lbl> <int> <dbl> <dbl>
## 1 1 1 [Excellent] 614 14.3 14.3
## 2 1 2 [Very good] 1805 41.9 56.2
## 3 1 3 [Good] 1361 31.6 87.8
## 4 1 4 [Fair] 443 10.3 98.1
## 5 1 5 [Poor] 80 1.9 100
## 6 2 1 [Excellent] 631 14.7 14.7
## 7 2 2 [Very good] 1878 43.6 58.3
## 8 2 3 [Good] 1310 30.4 88.7
## 9 2 4 [Fair] 409 9.5 98.2
## 10 2 5 [Poor] 74 1.7 99.9
## 11 2 NA 1 0 99.9
## 12 3 1 [Excellent] 574 13.3 13.3
## 13 3 2 [Very good] 1674 38.9 52.2
## 14 3 3 [Good] 1373 31.9 84.1
## 15 3 4 [Fair] 553 12.9 97
## 16 3 5 [Poor] 126 2.9 99.9
## 17 3 NA 3 0.1 100##
## Malaise Score Ranges by Wave:## # A tibble: 15 × 4
## # Groups: wave [3]
## wave malaise_range n percent
## <dbl> <chr> <int> <dbl>
## 1 1 0-2 (Low) 3399 79
## 2 1 3-5 (Moderate) 528 12.3
## 3 1 6-8 (High) 136 3.2
## 4 1 9+ (Very High) 6 0.1
## 5 1 Missing 234 5.4
## 6 2 0-2 (Low) 3388 78.7
## 7 2 3-5 (Moderate) 668 15.5
## 8 2 6-8 (High) 215 5
## 9 2 9+ (Very High) 8 0.2
## 10 2 Missing 24 0.6
## 11 3 0-2 (Low) 3409 79.2
## 12 3 3-5 (Moderate) 639 14.9
## 13 3 6-8 (High) 191 4.4
## 14 3 9+ (Very High) 4 0.1
## 15 3 Missing 60 1.4##
## GAD Score Distribution by Wave:## # A tibble: 42 × 5
## # Groups: wave [3]
## wave GAD n percent cum_percent
## <dbl> <dbl> <int> <dbl> <dbl>
## 1 1 4 2275 52.9 52.9
## 2 1 5 590 13.7 66.6
## 3 1 6 478 11.1 77.7
## 4 1 7 239 5.6 83.3
## 5 1 8 187 4.3 87.6
## 6 1 9 78 1.8 89.4
## 7 1 10 75 1.7 91.1
## 8 1 11 37 0.9 92
## 9 1 12 35 0.8 92.8
## 10 1 13 21 0.5 93.3
## # ℹ 32 more rows5. CORRELATION MATRIX BY WAVE
##
## === CORRELATION MATRICES BY WAVE ===##
## Attaching package: 'reshape2'## The following object is masked from 'package:tidyr':
##
## smiths
## 6. MISSING DATA ANALYSIS
##
## === MISSING DATA ANALYSIS ===## # A tibble: 3 × 14
## wave N_total GHQ_missing malaise_missing GAD_missing LONELY_missing
## <dbl> <int> <int> <int> <int> <int>
## 1 1 4303 0 234 217 227
## 2 2 4303 1 24 30 24
## 3 3 4303 3 60 62 56
## # ℹ 8 more variables: covid_positive_missing <int>, hospitalise_missing <int>,
## # GHQ_missing_percent <dbl>, malaise_missing_percent <dbl>,
## # GAD_missing_percent <dbl>, LONELY_missing_percent <dbl>,
## # covid_positive_missing_percent <dbl>, hospitalise_missing_percent <dbl>7. SUMMARY TABLE FOR PUBLICATION
##
## === PUBLICATION-READY SUMMARY TABLE ===## # A tibble: 3 × 8
## wave N GHQ_mean_sd malaise_mean_sd GAD_mean_sd LONELY_mean_sd
## <dbl> <int> <chr> <chr> <chr> <chr>
## 1 1 4303 2.44 (0.92) 1.21 (1.68) 5.32 (2.21) 5.44 (2)
## 2 2 4303 2.4 (0.91) 1.44 (1.85) 5.36 (2.21) 5.33 (1.99)
## 3 3 4303 2.53 (0.97) 1.36 (1.8) 5.45 (2.27) 5.66 (2.09)
## # ℹ 2 more variables: COVID_positive <chr>, Hospitalized <chr>##
## === ANALYSIS COMPLETE ===## This comprehensive descriptive analysis provides:## 1. Overall sample characteristics## 2. Descriptive statistics by wave for continuous variables## 3. Frequency distributions for categorical variables## 4. Detailed frequency tables## 5. Correlation matrices by wave## 6. Missing data analysis## 7. Publication-ready summary tableVisualising descriptive stats
Check the correlation / relationship between variables
Hypothesis 1: Having COVID will predict poorer mental health
Hypothesis 2: COVID severity predicts poorer mental health
1. DESCRIPTIVE COMPARISONS: COVID vs NO-COVID
## === COVID-19 AND MENTAL HEALTH PREDICTIVE ANALYSIS ===## 1. DESCRIPTIVE COMPARISONS BY COVID STATUS## # A tibble: 3 × 8
## covid_positive N N_unique_participants General Health Questionna…¹ Malaise
## <chr> <int> <int> <chr> <chr>
## 1 Covid Negative 11906 4151 2.45 (0.93) 1.31 (…
## 2 Covid Positive 947 534 2.52 (1) 1.57 (…
## 3 <NA> 56 53 2.45 (0.86) 2.05 (…
## # ℹ abbreviated name: ¹​`General Health Questionnaire`
## # ℹ 3 more variables: `Generalised Anxiety Disorder` <chr>,
## # `Loneliness Scale` <chr>, `Hospitalised Rate` <chr>2. SIMPLE T-TESTS FOR EACH MENTAL HEALTH OUTCOME
##
##
## 2. T-TESTS: COVID POSITIVE vs COVID NEGATIVE## # A tibble: 4 × 8
## Variable COVID_Mean No_COVID_Mean Difference t_statistic p_value Cohens_d
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 General Heal… 2.52 2.45 0.07 2.11 0.0349 0.076
## 2 Malaise 1.57 1.31 0.26 4.18 0 0.147
## 3 Generalised … 5.61 5.36 0.25 3.07 0.0022 0.112
## 4 Loneliness S… 5.62 5.46 0.16 2.23 0.0258 0.077
## # ℹ 1 more variable: Effect_Size <chr>3. LONGITUDINAL MIXED-EFFECTS MODELS
##
##
## 3. MIXED-EFFECTS MODELS: LONGITUDINAL ANALYSIS##
## Analyzing: General Health Questionnaire
## Basic Model AIC: 27067.81
## Enhanced Model AIC: 27069.53
## Hospitalization Effect: β = 0.061 , p = 0.5985
##
## Analyzing: Malaise
## Basic Model AIC: 42565.45
## Enhanced Model AIC: 42565.46
## Hospitalization Effect: β = 0.31 , p = 0.1587
##
## Analyzing: Generalised Anxiety Disorder
## Basic Model AIC: 49777.88
## Enhanced Model AIC: 49777.86
## Hospitalization Effect: β = 0.431 , p = 0.1544
##
## Analyzing: Loneliness Scale
## Basic Model AIC: 46610.69
## Enhanced Model AIC: 46612.69
## Hospitalization Effect: β = 0.009 , p = 0.9736## # A tibble: 8 × 7
## Variable Model COVID_Coefficient COVID_SE COVID_p_value COVID_CI_lower
## <chr> <chr> <dbl> <dbl> <dbl> <dbl>
## 1 General Health … Basi… 0.042 0.027 0.116 -0.01
## 2 General Health … Enha… 0.04 0.027 0.138 -0.013
## 3 Malaise Basi… 0.14 0.051 0.0065 0.039
## 4 Malaise Enha… 0.13 0.052 0.0125 0.028
## 5 Generalised Anx… Basi… 0.194 0.069 0.0052 0.058
## 6 Generalised Anx… Enha… 0.179 0.07 0.0106 0.042
## 7 Loneliness Scale Basi… 0.025 0.061 0.678 -0.094
## 8 Loneliness Scale Enha… 0.025 0.062 0.685 -0.096
## # ℹ 1 more variable: COVID_CI_upper <dbl>
## 4. TIMING ANALYSIS: WHEN DO EFFECTS APPEAR?
##
##
## 4. TIMING ANALYSIS: COVID EFFECTS BY WAVE## ========================================##
## Wave 1 Analysis:
##
## Wave 2 Analysis:
##
## Wave 3 Analysis:## # A tibble: 12 × 7
## Wave Variable COVID_Mean No_COVID_Mean Difference p_value Significant
## <int> <chr> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 1 General Health… 2.51 2.43 0.08 0.227 No
## 2 1 Malaise 1.45 1.2 0.25 0.0321 Yes
## 3 1 Generalised An… 5.56 5.3 0.26 0.114 No
## 4 1 Loneliness Sca… 5.72 5.43 0.29 0.0464 Yes
## 5 2 General Health… 2.33 2.4 -0.07 0.190 No
## 6 2 Malaise 1.66 1.41 0.25 0.0403 Yes
## 7 2 Generalised An… 5.59 5.34 0.25 0.0902 No
## 8 2 Loneliness Sca… 5.46 5.32 0.14 0.244 No
## 9 3 General Health… 2.66 2.52 0.14 0.0064 Yes
## 10 3 Malaise 1.59 1.33 0.26 0.0067 Yes
## 11 3 Generalised An… 5.65 5.43 0.22 0.0809 No
## 12 3 Loneliness Sca… 5.68 5.65 0.03 0.786 No5. HOSPITALIZATION AS SEVERITY INDICATOR
##
##
## 5. DOSE-RESPONSE ANALYSIS: COVID SEVERITY EFFECTS##
## General Health Questionnaire by COVID Severity:
## # A tibble: 3 × 4
## covid_severity N Mean SD
## <chr> <int> <dbl> <dbl>
## 1 COVID - Hospitalized 37 3.19 1.13
## 2 COVID - Not Hospitalized 910 2.49 0.99
## 3 No COVID 11906 2.45 0.93
## F-statistic: 12.325 , p-value: 0
##
## Malaise by COVID Severity:
## # A tibble: 3 × 4
## covid_severity N Mean SD
## <chr> <int> <dbl> <dbl>
## 1 COVID - Hospitalized 37 2.56 2.08
## 2 COVID - Not Hospitalized 910 1.54 1.81
## 3 No COVID 11906 1.31 1.77
## F-statistic: 14.978 , p-value: 0
##
## Generalised Anxiety Disorder by COVID Severity:
## # A tibble: 3 × 4
## covid_severity N Mean SD
## <chr> <int> <dbl> <dbl>
## 1 COVID - Hospitalized 37 6.57 3
## 2 COVID - Not Hospitalized 910 5.57 2.37
## 3 No COVID 11906 5.36 2.21
## F-statistic: 9.024 , p-value: 1e-04
##
## Loneliness Scale by COVID Severity:
## # A tibble: 3 × 4
## covid_severity N Mean SD
## <chr> <int> <dbl> <dbl>
## 1 COVID - Hospitalized 37 6.46 2.38
## 2 COVID - Not Hospitalized 910 5.59 2.04
## 3 No COVID 11906 5.46 2.03
## F-statistic: 5.863 , p-value: 0.00286. SUMMARY AND INTERPRETATION
##
##
## 6. SUMMARY AND INTERPRETATION## Key Findings:## 1. Descriptive comparisons show mean differences between COVID+ and COVID- groups## 2. T-tests provide statistical significance and effect sizes for group differences## 3. Mixed-effects models account for repeated measures and individual differences## 4. Wave-by-wave analysis shows when effects emerge or persist## 5. Severity analysis tests dose-response relationship## Interpretation Guide:## - Positive coefficients = COVID associated with WORSE mental health## - Negative coefficients = COVID associated with BETTER mental health## - p < 0.05 = statistically significant effect## - Cohen's d: 0.2=small, 0.5=medium, 0.8=large effect## Next Steps:## 1. Check model assumptions (residuals, normality)## 2. Consider additional covariates (age, gender, SES)## 3. Test for interaction effects (COVID × time)## 4. Consider lagged effects (COVID in wave X predicting MH in wave X+1)##
## === ANALYSIS COMPLETE ===Hypothesis 3: Lonliness and hospitalisation (COVID severity) are mediators between the relationship of COVID positivity and mental health (general anxiety & malaise).
SEM model with mediation
## Running SEM analysis to explore direct effect (COVID positive on loneliness, anxiety and malaise.## lavaan 0.6-19 ended normally after 16 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Used Total
## Number of observations 12430 12909
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## LONELY ~
## covd_pstv (a) 0.157 0.069 2.271 0.023 0.157 0.020
## GAD ~
## LONELY (b1) 0.583 0.008 70.143 0.000 0.583 0.532
## covd_pstv (c1) 0.146 0.064 2.281 0.023 0.146 0.017
## malaise ~
## LONELY (b2) 0.445 0.007 65.582 0.000 0.445 0.507
## covd_pstv (c2) 0.182 0.052 3.462 0.001 0.182 0.027
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .GAD ~~
## .malaise 1.958 0.031 62.878 0.000 1.958 0.683
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .LONELY 4.091 0.052 78.835 0.000 4.091 1.000
## .GAD 3.511 0.045 78.835 0.000 3.511 0.716
## .malaise 2.341 0.030 78.835 0.000 2.341 0.742
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect_GAD 0.092 0.040 2.270 0.023 0.092 0.011
## indirect_malas 0.070 0.031 2.270 0.023 0.070 0.010
## total_GAD 0.238 0.076 3.141 0.002 0.238 0.028
## total_malaise 0.252 0.061 4.137 0.000 0.252 0.037## The DAG diagram showing relationships between variables in SEM model 1## Plot coordinates for graph not supplied! Generating coordinates, see ?coordinates for how to set your own.
## The SEM model1-based path diagram.
## The second SEM model adding in hospitalisation as a second predictor.## lavaan 0.6-19 ended normally after 16 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 12
##
## Used Total
## Number of observations 12430 12909
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## LONELY ~
## covd_pstv (a1) 0.132 0.070 1.874 0.061 0.132 0.017
## hospitals (a2) 0.652 0.330 1.978 0.048 0.652 0.018
## GAD ~
## LONELY (b1) 0.583 0.008 70.113 0.000 0.583 0.532
## covd_pstv (c1) 0.130 0.065 1.998 0.046 0.130 0.015
## hospitals (c2) 0.413 0.306 1.352 0.176 0.413 0.010
## malaise ~
## LONELY (b2) 0.445 0.007 65.544 0.000 0.445 0.506
## covd_pstv (d1) 0.158 0.053 2.962 0.003 0.158 0.023
## hospitals (d2) 0.609 0.250 2.441 0.015 0.609 0.019
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .GAD ~~
## .malaise 1.957 0.031 62.874 0.000 1.957 0.683
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .LONELY 4.090 0.052 78.835 0.000 4.090 0.999
## .GAD 3.511 0.045 78.835 0.000 3.511 0.716
## .malaise 2.340 0.030 78.835 0.000 2.340 0.742
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect_GAD 0.077 0.041 1.873 0.061 0.077 0.009
## indrct_GAD_hsp 0.380 0.192 1.977 0.048 0.380 0.010
## indirect_malas 0.059 0.031 1.873 0.061 0.059 0.009
## indrct_mls_hsp 0.290 0.147 1.977 0.048 0.290 0.009
## total_GAD 1.001 0.355 2.818 0.005 1.001 0.045
## total_malaise 1.116 0.285 3.918 0.000 1.116 0.060## The DAG diagram of SEM model 2 which added hospitalisation as a separate predictor.## Plot coordinates for graph not supplied! Generating coordinates, see ?coordinates for how to set your own.
## The path diagram adding in Hospitalisation as a mediator (SEM model2).
## From To Weight
## 4 --> 1 1
## 5 --> 1 1
## 1 --> 2 1
## 4 --> 2 1
## 5 --> 2 1
## 1 --> 3 1
## 4 --> 3 1
## 5 --> 3 1
## 1 <-> 1 1
## 2 <-> 2 1
## 3 <-> 3 1
## 2 <-> 3 1
## 4 <-> 4 1
## 4 <-> 5 1
## 5 <-> 5 1
## 3 <-> 2 1
## 5 <-> 4 1Exploring longitudinal effects
## lavaan 0.6-19 ended normally after 161 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 58
##
## Used Total
## Number of observations 4250 4303
## Number of missing patterns 36
##
## Model Test User Model:
##
## Test statistic 1486.585
## Degrees of freedom 50
## P-value (Chi-square) 0.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## GAD_2 ~
## GAD_1 0.345 0.014 24.465 0.000 0.345 0.355
## GAD_3 ~
## GAD_2 0.471 0.015 30.764 0.000 0.471 0.462
## LONELY_2 ~
## LONELY_1 0.710 0.011 66.199 0.000 0.710 0.717
## LONELY_3 ~
## LONELY_2 0.781 0.011 70.313 0.000 0.781 0.737
## malaise_2 ~
## malaise_1 0.623 0.017 35.745 0.000 0.623 0.579
## malaise_3 ~
## malaise_2 0.539 0.013 41.801 0.000 0.539 0.560
## GAD_1 ~
## covid_positv_1 0.004 11.626 0.000 1.000 0.004 0.000
## hospitalise_1 -0.054 36.098 -0.001 0.999 -0.054 -0.001
## LONELY_1 0.329 36.239 0.009 0.993 0.329 0.297
## malaise_1 0.552 84.955 0.006 0.995 0.552 0.420
## GAD_2 ~
## covid_positv_2 0.059 0.077 0.770 0.441 0.059 0.007
## hospitalise_2 0.034 0.382 0.089 0.929 0.034 0.001
## LONELY_2 0.228 0.016 14.527 0.000 0.228 0.209
## malaise_2 0.505 0.024 21.362 0.000 0.505 0.425
## GAD_3 ~
## covid_positv_3 0.121 0.067 1.796 0.072 0.121 0.016
## hospitalise_3 -0.145 0.298 -0.485 0.628 -0.145 -0.004
## LONELY_3 0.229 0.015 14.984 0.000 0.229 0.218
## malaise_3 0.383 0.024 15.984 0.000 0.383 0.305
## malaise_1 ~
## covid_positv_1 0.118 4.285 0.027 0.978 0.118 0.016
## hospitalise_1 0.381 9.776 0.039 0.969 0.381 0.010
## LONELY_1 0.289 30.526 0.009 0.992 0.289 0.342
## GAD_1 0.243 54.065 0.005 0.996 0.243 0.319
## malaise_2 ~
## covid_positv_2 0.094 0.066 1.418 0.156 0.094 0.013
## hospitalise_2 0.435 0.337 1.290 0.197 0.435 0.012
## LONELY_2 0.183 0.014 12.859 0.000 0.183 0.199
## GAD_2 0.158 0.019 8.170 0.000 0.158 0.187
## malaise_3 ~
## covid_positv_3 0.127 0.050 2.548 0.011 0.127 0.022
## hospitalise_3 -0.018 0.222 -0.082 0.935 -0.018 -0.001
## LONELY_3 0.155 0.011 13.483 0.000 0.155 0.186
## GAD_3 0.220 0.014 15.481 0.000 0.220 0.276
## LONELY_1 ~
## covid_positv_1 0.316 0.137 2.302 0.021 0.316 0.036
## hospitalise_1 0.292 0.675 0.432 0.665 0.292 0.007
## LONELY_2 ~
## covid_positv_2 0.013 0.086 0.151 0.880 0.013 0.002
## hospitalise_2 1.016 0.422 2.410 0.016 1.016 0.026
## LONELY_3 ~
## covid_positv_3 0.029 0.075 0.391 0.696 0.029 0.004
## hospitalise_3 -0.441 0.333 -1.326 0.185 -0.441 -0.014
## GAD_2 ~
## LONELY_1 -0.053 0.015 -3.585 0.000 -0.053 -0.049
## GAD_3 ~
## LONELY_2 -0.071 0.016 -4.553 0.000 -0.071 -0.064
## malaise_2 ~
## LONELY_1 -0.067 0.013 -5.261 0.000 -0.067 -0.074
## malaise_3 ~
## LONELY_2 -0.077 0.011 -6.770 0.000 -0.077 -0.087
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .GAD_2 1.869 0.081 23.196 0.000 1.869 0.867
## .GAD_3 1.481 0.084 17.714 0.000 1.481 0.674
## .LONELY_2 1.453 0.062 23.298 0.000 1.453 0.736
## .LONELY_3 1.500 0.063 23.663 0.000 1.500 0.716
## .malaise_2 -0.792 0.076 -10.418 0.000 -0.792 -0.436
## .malaise_3 -1.086 0.060 -18.083 0.000 -1.086 -0.622
## .GAD_1 2.860 93.948 0.030 0.976 2.860 1.291
## .malaise_1 -1.653 121.657 -0.014 0.989 -1.653 -0.980
## .LONELY_1 5.427 0.032 170.273 0.000 5.427 2.719
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .GAD_2 1.532 0.036 42.804 0.000 1.532 0.330
## .GAD_3 1.595 0.039 40.491 0.000 1.595 0.331
## .LONELY_2 1.891 0.042 45.148 0.000 1.891 0.484
## .LONELY_3 2.004 0.044 45.718 0.000 2.004 0.457
## .malaise_2 1.136 0.035 32.707 0.000 1.136 0.345
## .malaise_3 0.883 0.022 40.189 0.000 0.883 0.290
## .GAD_1 2.282 108.991 0.021 0.983 2.282 0.465
## .malaise_1 1.453 100.102 0.015 0.988 1.453 0.510
## .LONELY_1 3.977 0.088 45.238 0.000 3.977 0.999Generating a DAG diagram of longitudinal effect
##
## Attaching package: 'ggdag'## The following object is masked from 'package:stats':
##
## filter
Generating path diagram for longitudinal SEM model.
## [1] "GAD_2" "GAD_3" "LONELY_2" "LONELY_3"
## [5] "malaise_2" "malaise_3" "GAD_1" "malaise_1"
## [9] "LONELY_1" "covid_positive_1" "hospitalise_1" "covid_positive_2"
## [13] "hospitalise_2" "covid_positive_3" "hospitalise_3"